Hybrid Deep Learning with Attention-Based Interpretability for PM2.5 Forecasting in Delhi Urban Environments

Mahasiva Saravagna Sai Lakshmi; Gollapudi SVSSVN Rithvik; CH V V Ramana; N Thirupathi Rao; Faten Khalid Karim; Ayman Aljarbouh; Samih M. Mostafa

doi:10.3791/71004

A subscription to JoVE is required to view this content. Sign in or start your free trial.

Research Article

Hybrid Deep Learning with Attention-Based Interpretability for PM_2.5 Forecasting in Delhi Urban Environments

253 views

⸱

DOI:

10.3791/71004

⸱

August 7th, 2026

Mahasiva Saravagna Sai Lakshmi¹ , Gollapudi SVSSVN Rithvik¹ , CH V V Ramana² , N Thirupathi Rao³ , Faten Khalid Karim⁴ , Ayman Aljarbouh⁵ , Samih M. Mostafa⁶

¹Department of AI&DS, Vignan's Institute of Information Technology, ²Vignan's Institute of Information Technology, ³Department of Computer Science and Engineering, Vignan's Institute of Information Technology, ⁴Department of Computer Sciences, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman University, ⁵Department of Software Engineering, College of Computer Engineering and Science, Prince Mohammad Bin Fahd University, ⁶Computer Science Department, Faculty of Computers and Information, Qena University

Summary

CORTA (Correlation Optimized Ranked Transfer-Attention)-Net, a hybrid deep learning framework for short-term PM₂.₅ forecasting in Delhi. The model combines CorrXGBoost-Rank feature selection, transfer learning with long short-term memory networks, and multi-head attention for temporal and feature-level interpretation and uses air-quality, meteorological, and satellite-derived fire-count data to improve PM_2.5 forecasting.

Abstract

Short-term PM_2.5 forecasting is challenging in Delhi because particulate matter concentrations are influenced by local emissions, meteorological variation, seasonal stagnation, and episodic fire-related pollution. This study presents CORTA-Net, a hybrid deep learning framework for PM_2.5 forecasting using multi-source environmental data from 2012 to 2024. The input data includes hourly air-quality observations from CPCB (Central Pollution Control Board) /DPCC (Delhi Pollution Control Committee) monitoring stations, meteorological variables from the India Meteorological Department (IMD), and satellite-derived fire-count information from MODIS (Moderate Resolution Imaging Spectroradiometer) products. The proposed framework first applies CorrXGBoost-Rank feature selection to reduce redundant predictors and retain important pollutants, meteorological, temporal, and fire-related variables. The selected features are then arranged as supervised sliding-window sequences and processed using a transfer-learning-based LSTM encoder followed by a multi-head attention layer. The attention mechanism provides feature- and time-step-level interpretation of the PM_2.5 forecast. CORTA-Net was evaluated using chronological training, testing, and validation partitions, as well as cross-validation. Compared with random forest, XGBoost, LSTM, and attention-LSTM baselines, the proposed framework reduced prediction error under the evaluated Delhi monitoring-station setting. The novelty of CORTA-Net lies in combining explicit CorrXGBoost-Rank feature screening, transfer-learning-based temporal encoding, MODIS fire-activity integration, and multi-head attention-based model-behavior analysis in a single reproducible PM_2.5 forecasting pipeline. Practically, the framework can support short-term urban air-quality forecasting in data-rich monitoring environments where pollutant records, meteorological observations, and fire-activity indicators are available.

Introduction

Fine particulate matter with aerodynamic diameter ≤ 2.5 µm (PM_2.5) is an important air-quality concern in Delhi because it is affected by local emissions¹^,²^,³, regional transport⁴, seasonal meteorology⁵, and episodic biomass-burning events⁶. During post-monsoon and winter periods⁷, low wind speed⁸, shallow boundary-layer conditions⁹, and temperature inversion can reduce pollutant dispersion and increase particula....